Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6041
    Prev
    Next
    INDEX
    Explanations

    code structures and definitions related to module creation and initialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessorType
    -0.58
     للمعارف
    -0.54
    vosti
    -0.52
    ?,?,
    -0.50
    complexType
    -0.48
     Bunting
    -0.48
    publique
    -0.47
    mula
    -0.46
    DebuggerStep
    -0.43
    ospels
    -0.43
    POSITIVE LOGITS
    rrggbb
    0.69
    LikeLike
    0.66
     שוליים
    0.66
     المعيارى
    0.60
    WebVitals
    0.56
     żad
    0.54
     Aucune
    0.53
     CURIAM
    0.52
    AnimationsModule
    0.52
     nessun
    0.51
    Activations Density 0.840%

    No Known Activations